{ "results": [ { "task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "bleu": 0.6460958847523566, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "bleu_stderr": 0.03922360003785139 }, { "task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge1_precision": 0.07760008602513783, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "rouge1_precision_stderr": 0.001320690166501572 }, { "task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge1_recall": 0.4207626130570328, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "rouge1_recall_stderr": 0.0051343858175420766 }, { "task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge1_fmeasure": 0.12269659017119199, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "rouge1_fmeasure_stderr": 0.0017597424238451932 }, { "task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge2_precision": 0.03635274690781486, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "rouge2_precision_stderr": 0.0008330185169416092 }, { "task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge2_recall": 0.2129557453468375, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "rouge2_recall_stderr": 0.003851289229933982 }, { "task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge2_fmeasure": 0.0577700863367864, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "rouge2_fmeasure_stderr": 0.001158809400479912 }, { "task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeL_precision": 0.07107029230772488, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "rougeL_precision_stderr": 0.001171387599016451 }, { "task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeL_recall": 0.38200909854824977, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "rougeL_recall_stderr": 0.004464667845112728 }, { "task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeL_fmeasure": 0.11231459598044416, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "rougeL_fmeasure_stderr": 0.0015694568258752962 }, { "task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeLsum_precision": 0.07356474812940257, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "rougeLsum_precision_stderr": 0.0012438027129333135 }, { "task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeLsum_recall": 0.39729543398826606, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "rougeLsum_recall_stderr": 0.004755911479219925 }, { "task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeLsum_fmeasure": 0.11625392090888889, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "rougeLsum_fmeasure_stderr": 0.0016649015391818642 } ], "config": { "model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-c4-repetitions/4b284b28bc4/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 4, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234 } }